Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 10236
    Prev
    Next
    INDEX
    Explanations

    references to programming frameworks, libraries, and components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.64
    elemField
    -0.55
    CodedInputStream
    -0.54
     iprot
    -0.53
    PullParser
    -0.52
    richTextPanel
    -0.52
    stateParams
    -0.48
     estekak
    -0.47
     mergeFrom
    -0.47
     Popcorn
    -0.47
    POSITIVE LOGITS
     Illuminate
    1.54
    Illuminate
    1.25
     django
    0.92
     XNUMX
    0.89
    BASEPATH
    0.89
    NUMX
    0.77
    zzleHttp
    0.69
    ftance
    0.64
    তথ্যসূত্র
    0.64
    Discografia
    0.64
    Activations Density 0.018%

    No Known Activations